Upload Date | September 18 2024 01:00 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1425
265.0 IPS |
|
Image Classification (HP)
|
100% |
10102
1.88 KIPS |
|
Image Classification (Q)
|
97% |
13017
2.43 KIPS |
|
Image Segmentation (SP)
|
100% |
1460
23.7 IPS |
|
Image Segmentation (HP)
|
100% |
12150
197.0 IPS |
|
Image Segmentation (Q)
|
99% |
12958
210.1 IPS |
|
Pose Estimation (SP)
|
100% |
6885
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
98933
115.4 IPS |
|
Pose Estimation (Q)
|
95% |
102963
120.7 IPS |
|
Object Detection (SP)
|
100% |
1577
125.1 IPS |
|
Object Detection (HP)
|
100% |
12876
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14873
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3058
36.3 IPS |
|
Face Detection (HP)
|
100% |
30650
364.2 IPS |
|
Face Detection (Q)
|
100% |
38664
459.4 IPS |
|
Depth Estimation (SP)
|
100% |
6189
47.7 IPS |
|
Depth Estimation (HP)
|
99% |
75149
579.0 IPS |
|
Depth Estimation (Q)
|
85% |
96986
758.3 IPS |
|
Style Transfer (SP)
|
100% |
18535
23.8 IPS |
|
Style Transfer (HP)
|
100% |
167482
215.3 IPS |
|
Style Transfer (Q)
|
96% |
172272
222.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4225
156.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
32348
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
39848
1.47 KIPS |
|
Text Classification (SP)
|
100% |
2667
3.56 KIPS |
|
Text Classification (HP)
|
100% |
2283
3.05 KIPS |
|
Text Classification (Q)
|
93% |
2329
3.13 KIPS |
|
Machine Translation (SP)
|
100% |
3471
59.8 IPS |
|
Machine Translation (HP)
|
100% |
2383
41.1 IPS |
|
Machine Translation (Q)
|
98% |
2336
40.4 IPS |